Majlis Academy · Bootcamp

ADLC bootcamp

AI in the engineering delivery lifecycle

Most engineering teams use AI only while they write code. They do not know what each task costs, and they cannot prove that AI-assisted work meets the requirement. In five days, your team learns to use AI from intake to release, at a known cost, with evidence and human approval at each gate.

Email contact@majlisofai.com See the five days

The questions we answer

Three questions your team returns to all week.

Where in our delivery lifecycle does AI add value, and where does it only add cost?

What evidence proves that AI-assisted work meets the requirement?

Which decisions must a person keep, and why?

The ADLC reference model

Three layers that stay the same when tools change

Delivery

The lifecycle your engineers already know.

Requirement intake
Analysis and decomposition
Planning
Implementation
Testing and verification
Release
Change and improvement

AI execution

How AI takes part in each stage.

Prompts as specifications
Context and repository grounding
Model routing
Tool use
Specialist agents
Review loops

Governance

What makes it safe in a regulated institution.

Token and cost control
Security and compliance
Human approval gates
Quality evidence
Production readiness
Audit and accountability

Aligned with NIST AI RMF, ISO/IEC 42001, the EU AI Act (Article 14, human oversight), TOGAF and the Well-Architected Framework.

Five days, in lifecycle order

5 learner hours each day

Baseline and token economics
2.5 h practice · 2.5 h input
Specification and context
3 h practice · 2 h input
Planning and agentic implementation
3.25 h practice · 1.75 h input
Verification and production readiness
4 h practice · 1 h input
risk, security and architecture join
Governance, loops and adoption
3.75 h practice · 1.25 h input
risk, security and architecture join

Twelve outcomes

Each one is practised and checked

#	After the course, the learner can	Level and practice	Practice
Day 1Baseline and token economics
01	Map AI use and record a delivery baseline Map your team's AI use onto the ADLC reference model, with the time, quality and cost of three real tasks.	Analyse ArchiMate modelling	1 h
02	Design a model routing rule set Design a model routing rule set for five task types and show the change in cost per task against the baseline.	Create Hands-on case	1.5 h
Day 2Specification and context
03	Rewrite a prompt as a specification Rewrite a prompt from your team as a specification-grade prompt with acceptance criteria, an output contract and a verification check.	Apply Gallery walk	1.5 h
04	Configure repository context Configure the project context of one repository with a rules file and a context-loading pattern that keeps token use within a stated limit.	Apply Hands-on case	1.5 h
Day 3Planning and agentic implementation
05	Decompose a requirement with approval points Break down one requirement into delivery, implementation and verification tasks, and mark the approval point for each task.	Analyse Hands-on case	1.25 h
06	Run a plan-then-execute agent flow Run a plan-then-execute agent flow on a code change with defined stop conditions, escalation points and guardrails.	Apply Branching case	2 h
Day 4Verification and production readiness
07	Trace acceptance criteria to tests Trace each acceptance criterion of a requirement to its verification checks, and find the gaps and the noisy tests.	Analyse Hands-on case	1.5 h
08	Build a verification agent Build a verification agent that checks a pull request against its acceptance criteria and test evidence, and escalates defined cases to a person.	Create Hands-on case	1.5 h
09	Assess production readiness Assess an AI-assisted change against a production readiness definition and justify a go or no-go decision with evidence.	Evaluate Review-panel role-play	1 h
Day 5Governance, loops and adoption
10	Design an intake checklist and review agent Design an AI intake checklist and a review agent that classifies each control as pass, fail or escalate.	Create Hands-on case	1.5 h
11	Design a controlled feedback loop Design one feedback loop for a real process with an evaluation signal, a stop condition and a cost boundary.	Create Hands-on case	1.25 h
12	Justify an adoption and ownership plan Justify an adoption plan that names the owner, the next step and the sponsor of each artefact that the course produced.	Evaluate Wardley mapping	1 h

What your team keeps

Working assets, not slides

Every outcome produces an asset that your team owns after the course. We build them on your repositories and planning system where your policies allow, or on our synthetic Sandbox Bank.

ADLC reference model view
Baseline task set
Cost-per-task comparison
Routing rule set
Specification-grade prompts
Repository context pattern
Decomposition example
Requirement-to-planning flow
Agent flow and run log
Traceability map
Verification agent
Production readiness definition
Intake checklist
Intake review agent
Feedback loop design
Adoption and ownership plan

How we measure success

Kirkpatrick levels 1 to 4

Level 1 · Reaction

80 %

of learners rate the course useful for their daily work

End of course

Level 2 · Learning

85 %

of learners pass the graded work of all twelve outcomes

End of course

Level 3 · Behaviour

teams use the routing rules and the verification agent on live work

After 60 days

Level 4 · Results

Lower

average cost per task against the day 1 baseline, with review quality held

After 90 days

Practical details

Who should attend: Software engineers, QA engineers, tech leads and platform engineers. Risk, security and architecture colleagues join on days 4 and 5.
Before the course: Daily use of Git, a CI pipeline and a planning system. Some use of an AI coding assistant.
Delivery: Classroom, at your site. Five days of 5 learner hours, with micro-lessons of 6 to 12 minutes between practice blocks.
Language: English, with an English–Arabic glossary of ADLC terms.
Tools and data: Only the AI tools and models that your organisation approves. Exercises use synthetic data unless your data owner approves otherwise.
Your sector: We adapt the cases to banking (BIAN), telco (TM Forum ODA, eTOM, SID) or government.
After the course: A one-page ADLC job aid, two office-hours sessions at 2 and 6 weeks, and a review of your adoption plan at 30 days.

Plan a cohort

Bring one team and one real requirement.

Write to us with your sector, the size of your team and the dates you have in mind. We reply with a proposed plan for your environment.

Email contact@majlisofai.com